{"id":"https://openalex.org/W4416749698","doi":"https://doi.org/10.1109/iros60139.2025.11246626","title":"Ag2x2: Robust Agent-Agnostic Visual Representations for Zero-Shot Bimanual Manipulation","display_name":"Ag2x2: Robust Agent-Agnostic Visual Representations for Zero-Shot Bimanual Manipulation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416749698","doi":"https://doi.org/10.1109/iros60139.2025.11246626"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11246626","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246626","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Ziyin Xiong","orcid":null},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4392738278","display_name":"Beijing Institute for General Artificial Intelligence","ror":"https://ror.org/02kw1ws04","country_code":"CN","type":"government","lineage":["https://openalex.org/I4392738278"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyin Xiong","raw_affiliation_strings":["Beijing Institute for General Artificial Intelligence (BIGAI),National Key Laboratory of General Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute for General Artificial Intelligence (BIGAI),National Key Laboratory of General Artificial Intelligence","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4392738278"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102997673","display_name":"Yinghan Chen","orcid":"https://orcid.org/0009-0000-6922-3358"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4392738278","display_name":"Beijing Institute for General Artificial Intelligence","ror":"https://ror.org/02kw1ws04","country_code":"CN","type":"government","lineage":["https://openalex.org/I4392738278"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinghan Chen","raw_affiliation_strings":["Beijing Institute for General Artificial Intelligence (BIGAI),National Key Laboratory of General Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute for General Artificial Intelligence (BIGAI),National Key Laboratory of General Artificial Intelligence","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4392738278"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023051708","display_name":"Puhao Li","orcid":"https://orcid.org/0009-0003-2696-9346"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4392738278","display_name":"Beijing Institute for General Artificial Intelligence","ror":"https://ror.org/02kw1ws04","country_code":"CN","type":"government","lineage":["https://openalex.org/I4392738278"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Puhao Li","raw_affiliation_strings":["Beijing Institute for General Artificial Intelligence (BIGAI),National Key Laboratory of General Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute for General Artificial Intelligence (BIGAI),National Key Laboratory of General Artificial Intelligence","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4392738278"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100544330","display_name":"Yixin Zhu","orcid":"https://orcid.org/0000-0003-3319-2961"},"institutions":[{"id":"https://openalex.org/I111483173","display_name":"King University","ror":"https://ror.org/01evb6z23","country_code":"US","type":"education","lineage":["https://openalex.org/I111483173"]},{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Yixin Zhu","raw_affiliation_strings":["Peking University,School of Psychological and Cognitive Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University,School of Psychological and Cognitive Sciences","institution_ids":["https://openalex.org/I111483173","https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100668020","display_name":"Tengyu Liu","orcid":"https://orcid.org/0000-0003-4006-1740"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4392738278","display_name":"Beijing Institute for General Artificial Intelligence","ror":"https://ror.org/02kw1ws04","country_code":"CN","type":"government","lineage":["https://openalex.org/I4392738278"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tengyu Liu","raw_affiliation_strings":["Beijing Institute for General Artificial Intelligence (BIGAI),National Key Laboratory of General Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute for General Artificial Intelligence (BIGAI),National Key Laboratory of General Artificial Intelligence","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4392738278"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101529675","display_name":"Siyuan Huang","orcid":"https://orcid.org/0009-0009-6943-7116"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4392738278","display_name":"Beijing Institute for General Artificial Intelligence","ror":"https://ror.org/02kw1ws04","country_code":"CN","type":"government","lineage":["https://openalex.org/I4392738278"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siyuan Huang","raw_affiliation_strings":["Beijing Institute for General Artificial Intelligence (BIGAI),National Key Laboratory of General Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute for General Artificial Intelligence (BIGAI),National Key Laboratory of General Artificial Intelligence","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4392738278"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.49486273,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12224","last_page":"12231"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.8392999768257141,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.8392999768257141,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.042100001126527786,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.030799999833106995,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5860999822616577},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.5383999943733215},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5072000026702881},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.499099999666214},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4327999949455261},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4000000059604645},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.37700000405311584}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7497000098228455},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6258000135421753},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5860999822616577},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.5383999943733215},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5072000026702881},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.499099999666214},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4327999949455261},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4275999963283539},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4000000059604645},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.37700000405311584},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.34880000352859497},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3249000012874603},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.320499986410141},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.31189998984336853},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.30869999527931213},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.29109999537467957},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2888999879360199},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.28130000829696655},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.28060001134872437}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11246626","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246626","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1164749991","https://openalex.org/W2117539524","https://openalex.org/W2147168033","https://openalex.org/W2464089775","https://openalex.org/W2951360122","https://openalex.org/W3006398608","https://openalex.org/W3021013305","https://openalex.org/W3035198432","https://openalex.org/W3199740299","https://openalex.org/W3214952050","https://openalex.org/W4299959846","https://openalex.org/W4312655706","https://openalex.org/W4366386348","https://openalex.org/W4384518901","https://openalex.org/W4385430674","https://openalex.org/W4386075819","https://openalex.org/W4389352485","https://openalex.org/W4401414765","https://openalex.org/W4401691802","https://openalex.org/W4402353996","https://openalex.org/W4402704593","https://openalex.org/W4405785673","https://openalex.org/W4413145126"],"related_works":[],"abstract_inverted_index":{"Bimanual":[0],"manipulation,":[1],"fundamental":[2],"to":[3,12],"human":[4,35,154],"daily":[5],"activities,":[6],"remains":[7],"a":[8,55,83,137,161],"challenging":[9,97],"task":[10],"due":[11],"its":[13],"inherent":[14],"complexity":[15],"of":[16,25,115,166],"coordinated":[17],"control.":[18],"Recent":[19],"advances":[20],"have":[21],"enabled":[22],"zero-shot":[23],"learning":[24,165],"single-arm":[26],"manipulation":[27,60],"skills":[28],"through":[29,61,127],"agent-agnostic":[30],"visual":[31,63],"representations":[32,64,125],"derived":[33],"from":[34,92],"videos;":[36],"however,":[37],"these":[38],"methods":[39,108],"overlook":[40],"crucial":[41],"agentspecific":[42],"information":[43],"necessary":[44],"for":[45,58,133,140],"bimanual":[46,59,90,168],"coordination,":[47],"such":[48],"as":[49],"end-effector":[50],"positions.":[51],"We":[52],"propose":[53],"Ag2x2,":[54],"computational":[56],"framework":[57],"coordination-aware":[62],"that":[65,80,124],"jointly":[66],"encode":[67],"object":[68],"states":[69],"and":[70,94,109],"hand":[71],"motion":[72],"patterns":[73],"while":[74],"maintaining":[75,147],"agent-agnosticism.":[76],"Extensive":[77],"experiments":[78],"demonstrate":[79],"Ag2x2":[81,128,159],"achieves":[82],"73.5%":[84],"success":[85,113],"rate":[86,114],"across":[87,150],"13":[88],"diverse":[89,151],"tasks":[91,152],"Bi-DexHands":[93],"PerAct2,":[95],"including":[96],"scenarios":[98],"with":[99,118],"deformable":[100],"objects":[101],"like":[102],"ropes.":[103],"This":[104],"performance":[105,149],"outperforms":[106],"baseline":[107],"even":[110],"surpasses":[111],"the":[112],"policies":[116],"trained":[117],"expert-engineered":[119],"rewards.":[120],"Furthermore,":[121],"we":[122],"show":[123],"learned":[126],"can":[129],"be":[130],"effectively":[131],"leveraged":[132],"imitation":[134],"learning,":[135],"establishing":[136],"scalable":[138,164],"pipeline":[139],"skill":[141],"acquisition":[142],"without":[143,153],"expert":[144],"supervision.":[145],"By":[146],"robust":[148],"demonstrations":[155],"or":[156],"engineered":[157],"rewards,":[158],"represents":[160],"step":[162],"toward":[163],"complex":[167],"robotic":[169],"skills.":[170]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-28T00:00:00"}